search

Hironsan / anago

Bidirectional LSTM-CRF and ELMo for Named-Entity Recognition, Part-of-Speech Tagging and so on.
https://anago.herokuapp.com/
MIT License
1.48k stars 371 forks source link

Save Trained Model. #63

Closed xain123 closed 6 years ago

xain123 commented 6 years ago

I have trained the model on my data set according to the instructions. But i didn't find any way to save the trained model. Is there any way?

nkansal96 commented 6 years ago

This is what I'm using to save the model:

model = anago.Sequence()
model.train(X, y, x_test, y_test)
model.save(args.model_dir)
xain123 commented 6 years ago

Thanks

On Wed, 23 May 2018 at 3:22 AM, Nikhil Kansal notifications@github.com wrote:

This is what I'm using to save the model:

model = anago.Sequence() model.train(X, y, x_test, y_test) model.save(args.model_dir)

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/Hironsan/anago/issues/63#issuecomment-391159650, or mute the thread https://github.com/notifications/unsubscribe-auth/Aey1ODCzIMz3XPdeXyKwCBunzQifNLdiks5t1I-zgaJpZM4UJHdP .

xain123 commented 6 years ago

image i an facing this issue while traning

nkansal96 commented 6 years ago

I think this happens if your dataset is too small. There is another issue open for this.